Dockerfile.backend.cuda

FROM nvidia/cuda:12.8.1-devel-ubuntu24.04

# Set working directory
WORKDIR /app

# Add build argument to conditionally skip llama.cpp build
ARG SKIP_LLAMA_BUILD=false

# Install system dependencies with noninteractive mode to avoid prompts
RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y \
    build-essential cmake git curl wget lsof vim unzip sqlite3 \
    python3-pip python3-venv python3-full python3-poetry pipx \
    && apt-get clean \
    && rm -rf /var/lib/apt/lists/* \
    && ln -sf /usr/bin/python3 /usr/bin/python

# Create a virtual environment to avoid PEP 668 restrictions
RUN python -m venv /app/venv
ENV PATH="/app/venv/bin:$PATH"
ENV VIRTUAL_ENV="/app/venv"

# Use the virtual environment's pip to install packages
RUN pip install --upgrade pip \
    && pip install poetry \
    && poetry config virtualenvs.create false

# Create directories
RUN mkdir -p /app/dependencies /app/data/sqlite /app/data/chroma_db /app/logs /app/run /app/resources

# Copy dependency files - Files that rarely change
COPY dependencies/graphrag-1.2.1.dev27.tar.gz /app/dependencies/
COPY dependencies/llama.cpp.zip /app/dependencies/

# Copy GPU checker script
COPY docker/app/check_gpu_support.sh /app/
COPY docker/app/check_torch_cuda.py /app/
RUN chmod +x /app/check_gpu_support.sh

# Unpack llama.cpp and build with CUDA support (conditionally, based on SKIP_LLAMA_BUILD)
RUN if [ "$SKIP_LLAMA_BUILD" = "false" ]; then \
        echo "=====================================================================" && \
        echo "STARTING LLAMA.CPP BUILD WITH CUDA SUPPORT - THIS WILL TAKE SOME TIME" && \
        echo "=====================================================================" && \
        LLAMA_LOCAL_ZIP="dependencies/llama.cpp.zip" && \
        echo "Using local llama.cpp archive..." && \
        unzip -q "$LLAMA_LOCAL_ZIP" && \
        cd llama.cpp && \
        mkdir -p build && \
        cd build && \
        echo "Starting CMake configuration with CUDA support..." && \
        cmake -DGGML_CUDA=OFF  -DLLAMA_CUBLAS=OFF \
              -DCMAKE_BUILD_TYPE=Release \
              -DBUILD_SHARED_LIBS=OFF \
              -DLLAMA_NATIVE=ON \
              .. && \
        echo "Starting build process (this will take several minutes)..." && \
        cmake --build . --config Release -j --verbose && \
        echo "Build completed successfully" && \
        chmod +x /app/llama.cpp/build/bin/llama-server /app/llama.cpp/build/bin/llama-cli && \
        echo "====================================================================" && \
        echo "CUDA BUILD COMPLETED SUCCESSFULLY! GPU ACCELERATION IS NOW AVAILABLE" && \
        echo "===================================================================="; \
    else \
        echo "=====================================================================" && \
        echo "SKIPPING LLAMA.CPP BUILD (SKIP_LLAMA_BUILD=$SKIP_LLAMA_BUILD)" && \
        echo "Using existing llama.cpp build from Docker volume" && \
        echo "=====================================================================" && \
        LLAMA_LOCAL_ZIP="dependencies/llama.cpp.zip" && \
        echo "Just unpacking llama.cpp archive (no build)..." && \
        unzip -q "$LLAMA_LOCAL_ZIP" && \
        cd llama.cpp && \
        mkdir -p build; \
    fi

# Mark as GPU-optimized build for runtime reference
RUN mkdir -p /app/data && \
    echo "{ \"gpu_optimized\": true, \"optimized_on\": \"$(date -u +\"%Y-%m-%dT%H:%M:%SZ\")\" }" > /app/data/gpu_optimized.json && \
    echo "Created GPU-optimized marker file"

# Copy project configuration - Files that occasionally change
COPY pyproject.toml README.md /app/

# Fix for potential package installation issues with Poetry
RUN pip install --upgrade setuptools wheel
RUN poetry install --no-interaction --no-root || poetry install --no-interaction --no-root --without dev
RUN pip install --force-reinstall dependencies/graphrag-1.2.1.dev27.tar.gz

# Copy source code - Files that frequently change
COPY docker/ /app/docker/
COPY lpm_kernel/ /app/lpm_kernel/

# Check module import
RUN python -c "import lpm_kernel; print('Module import check passed')"

# Set environment variables
ENV PYTHONUNBUFFERED=1 \
    PYTHONPATH=/app \
    BASE_DIR=/app/data \
    LOCAL_LOG_DIR=/app/logs \
    RUN_DIR=/app/run \
    RESOURCES_DIR=/app/resources \
    APP_ROOT=/app \
    FLASK_APP=lpm_kernel.app \
    LD_LIBRARY_PATH=/usr/local/cuda/lib64:$LD_LIBRARY_PATH

# Expose ports
EXPOSE 8002 8080

# Set the startup command
CMD ["bash", "-c", "echo 'Checking SQLite database...' && if [ ! -s /app/data/sqlite/lpm.db ]; then echo 'SQLite database not found or empty, initializing...' && mkdir -p /app/data/sqlite && sqlite3 /app/data/sqlite/lpm.db '.read /app/docker/sqlite/init.sql' && echo 'SQLite database initialized successfully' && echo 'Tables created:' && sqlite3 /app/data/sqlite/lpm.db '.tables'; else echo 'SQLite database already exists, skipping initialization'; fi && echo 'Checking ChromaDB...' && if [ ! -d /app/data/chroma_db/documents ] || [ ! -d /app/data/chroma_db/document_chunks ]; then echo 'ChromaDB collections not found, initializing...' && python /app/docker/app/init_chroma.py && echo 'ChromaDB initialized successfully'; else echo 'ChromaDB already exists, skipping initialization'; fi && echo 'Starting application at ' $(date) >> /app/logs/backend.log && cd /app && python -m flask run --host=0.0.0.0 --port=${LOCAL_APP_PORT:-8002} >> /app/logs/backend.log 2>&1"]